Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 492 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0682. Min Range: -7.0682
Max Act: 7.0682. Min Act: -0.1700
Data Index: 7593701 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0682. Min Range: -7.0682
Max Act: 6.5994. Min Act: -0.1700
Data Index: 3643008 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0682. Min Range: -7.0682
Max Act: 6.5057. Min Act: -0.1700
Data Index: 4034795 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0682. Min Range: -7.0682
Max Act: 6.4432. Min Act: -0.1700
Data Index: 1675564 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0682. Min Range: -7.0682
Max Act: 6.4432. Min Act: -0.1700
Data Index: 6297021 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0682. Min Range: -7.0682
Max Act: 6.3807. Min Act: -0.1700
Data Index: 4298836 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0682. Min Range: -7.0682
Max Act: 6.3807. Min Act: -0.1700
Data Index: 1139652 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0682. Min Range: -7.0682
Max Act: 6.3807. Min Act: -0.1700
Data Index: 3784290 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0682. Min Range: -7.0682
Max Act: 6.2869. Min Act: -0.1700
Data Index: 583162 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0682. Min Range: -7.0682
Max Act: 6.3182. Min Act: -0.1700
Data Index: 3054883 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0682. Min Range: -7.0682
Max Act: 6.1619. Min Act: -0.1700
Data Index: 4054561 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0682. Min Range: -7.0682
Max Act: 6.1932. Min Act: -0.1700
Data Index: 4581444 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0682. Min Range: -7.0682
Max Act: 6.2244. Min Act: -0.1700
Data Index: 7456475 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0682. Min Range: -7.0682
Max Act: 6.1932. Min Act: -0.1700
Data Index: 4318068 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0682. Min Range: -7.0682
Max Act: 6.1619. Min Act: -0.1700
Data Index: 8813016 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0682. Min Range: -7.0682
Max Act: 6.1307. Min Act: -0.1700
Data Index: 4909953 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0682. Min Range: -7.0682
Max Act: 6.1619. Min Act: -0.1700
Data Index: 4215685 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0682. Min Range: -7.0682
Max Act: 6.1932. Min Act: -0.1700
Data Index: 1954525 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0682. Min Range: -7.0682
Max Act: 6.1619. Min Act: -0.1700
Data Index: 1112172 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0682. Min Range: -7.0682
Max Act: 6.1307. Min Act: -0.1700
Data Index: 6378629 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19